Models & routing
IsonAI offers three model tiers with different capabilities and speeds. Omni is the default; you can switch to a different tier at any time from the model picker in the chat top bar, and your choice stays in effect until you change it.
Terms used in these docs: tier/model is the engine that answers (Omni, LYT, PRME); mode is a behavior setting on top of it (Thinking for reasoning depth).
IsonAI Omni (default)
The default tier for everyday to complex work: layered analysis, long reasoning, thorough comparisons, structured writing, and agentic behavior such as search-read-conclude across sources. Omni is also the tier for images, audio, and documents, and it is the engine behind Naya and Deep Research. It is the tier every new conversation starts on.
IsonAI LYT
The lightweight tier that prioritizes speed — for casual conversation, greetings, and simple everyday questions. LYT does not use the daily quota, so it stays available when the smart-model quota runs out. Its capabilities are more limited: web search is more concise and there is no deep reasoning. On LYT, Thinking always behaves as Fast.
PRME
IsonAI's most capable tier — deepest reasoning for the hardest problems, with coding and mathematics among its strengths rather than its definition. PRME reads images and documents as well. It is only active when selected explicitly; no other tier routes questions to it automatically.
Explicit selection
Your choice in the model picker is always respected. If you lock Omni, every question is answered by Omni; the same goes for LYT and PRME. IsonAI does not choose a tier for you and never silently substitutes one tier for another — the only automatic change is the quota fallback described below.
Fallback and degradation
- Quota exhausted — when the daily smart-model quota runs out, answers automatically continue on LYT until the quota renews, with a notice in the interface. See Plans & quota.
- Tier outage — if a tier's engine is temporarily unavailable, the picker marks it UNAVAILABLE with a clear message instead of silently answering with another tier. Switch to a different tier yourself; nothing is substituted for you.
Choosing the right tier
| Need | Choice |
|---|---|
| Everyday use, deep analysis, long documents, important decisions, images and audio | Omni |
| Light chat as fast as possible, quota-friendly | LYT |
| The hardest problems: deep reasoning, code, math | PRME |
Related
- Thinking — reasoning depth on top of any tier.
- Plans & quota — daily quota per tier.
Last verified: